duyet
- 139 skills
- 0 followers
- 305 repo stars
- last month last updated
- ▌ Interview 2 · duyetConduct in-depth requirements interview using Socratic questioning to clarify implementation details
- ▌ Orchestration 3 · duyetMANDATORY - You must load this skill before doing anything else. This defines how you operate.
- ▌ Quality Gates 2 · duyetSystematic quality verification procedures for code review and delivery. Use when validating completed work, conducting code reviews, or ensuring production readiness.
- ▌ Frontend Design 3 · duyet bundleCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
- ▌ Task Loop 2 · duyetIterative execution methodology. Small steps, verify each, adapt based on results.
- ▌ Clickhouse 2 · duyet bundleMUST USE when reviewing ClickHouse schemas, queries, or configurations. Contains 28 rules that MUST be checked before providing recommendations. Always read relevant rule files and cite specific rules in responses.
- ▌ Transparency 2 · duyetPatterns for showing thinking process and execution chain. Every step visible, every decision traceable.
- ▌ Orchestration 2 · duyet bundleOrchestrate complex work through parallel agent coordination. Decompose requests into task graphs, spawn background workers, and synthesize results elegantly. Use for multi-component features, large investigations, or any work benefiting from parallelization.
- ▌ Duyet Knowledge 2 · duyetMaintain and update knowledge base about Duyet Le (@duyet) - profile, resume, blog posts, projects.
- ▌ Frontend Design 2 · duyet bundleCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
- ▌ Prompt Engineering 2 · duyet bundleComprehensive prompt engineering guidance for Claude (Anthropic), Gemini (Google), and Grok (xAI). Use when crafting prompts to leverage each model's unique capabilities—XML-style tags for Claude, system instructions for Gemini, conversational style for Grok.
- ▌
- ▌ Build Agent 2 · duyet bundleBuild an AI-agent application end-to-end — from an empty repo or an existing codebase. Use when the user wants to "build an agent", "scaffold an agent app", "add an agent API", "build an agent UI/chat", "pick an agent framework", or set up tool calling, tracing, or an AI gateway. Interviews the user when requirements are unclear; detects the stack when a project already exists. Knows LangGraph, DeepAgents, Vercel AI SDK, Cloudflare Agents SDK, TanStack AI, Google ADK, and the Claude Agent SDK. Always verifies against live official docs (Context7 / llms.txt / WebFetch) before writing code.
- ▌ Setup Polar 2 · duyetInteractive onboarding wizard to set up Polar payment integration from scratch. Use this skill when: (1) User wants to "set up Polar" or "integrate Polar" in their project; (2) User is starting fresh with Polar and needs guided setup; (3) User asks "how do I get started with Polar"; (4) User wants to add payments/subscriptions/checkout to their app using Polar; (5) User needs help creating their first Polar product and checkout. This skill walks through MCP installation, authentication, product creation, and generates framework-specific integration code.
- ▌ UI UX Audit 2 · duyet bundleAutomated UI/UX + accessibility audit for the ClickHouse Monitor dashboard (apps/dashboard-tsr). Use this whenever the user wants to "test all pages", "audit the dashboard", "find UI/UX issues", "check accessibility / a11y", "spot visual regressions", "screenshot every route", "reproduce a UI bug", or asks to verify the dashboard UI after a change or deploy. It sweeps every dashboard route headlessly, captures console errors + failed network calls, runs axe-core accessibility scans, detects layout overflow and stuck loading skeletons, diffs screenshots against a baseline for visual regression, and emits a runnable repro (trace.zip + script) for each issue so it can be replayed on demand. Runs against the local dev server (auth bypassed) by default, or the live Clerk-protected deployment using the stored test session. Prefer this over ad-hoc one-off Playwright scripts for any multi-page UI check.
- ▌ Polar Testing 2 · duyetGuide for testing Polar payment integrations using the sandbox environment. Use this skill when: (1) Setting up the Polar sandbox for development; (2) Testing checkout flows without real payments; (3) Using Stripe test cards with Polar; (4) Writing integration tests for payment flows; (5) Testing webhooks locally with ngrok; (6) Mocking Polar in unit tests; (7) Setting up CI/CD pipelines with Polar sandbox; (8) Debugging payment issues in sandbox.
- ▌ Hardware Tuning 2 · duyetDetect server cores/RAM/disk from system tables, then recommend ClickHouse settings sized to that hardware.
- ▌ Plan And Verify 2 · duyetDecompose multi-step tasks into an explicit update_plan checklist, then verify each result before stating it as fact.
- ▌ Polar Migration 2 · duyetGuide for migrating to Polar from other payment platforms (Stripe Billing, Paddle, Lemon Squeezy, Gumroad). Use this skill when: (1) Planning a migration from another payment provider to Polar; (2) Migrating customer data and subscriptions; (3) Running parallel systems during transition; (4) Mapping products and pricing between platforms; (5) Handling payment method migration; (6) Communicating migration to customers; (7) Testing migration in sandbox before production.
- ▌ Troubleshooting 2 · duyetDiagnose and resolve ClickHouse issues: OOM, slow merges, stuck mutations, query failures with error codes, and systematic error clustering.
- ▌ Anomaly Detection 2 · duyetDetect cluster abnormalities by comparing recent activity (last 1h) to a baseline (preceding 24h) using the raw query tool.
- ▌ Concept Explainer 2 · duyetExplains core ClickHouse concepts with accurate mental models — MergeTree, indexes, replication, sharding, and special engines.
- ▌ Polar Integration 2 · duyetAdd Polar billing to a TypeScript/JavaScript app using the @polar-sh/sdk package. Use this skill whenever the user wants to add a Checkout endpoint, a Customer Portal endpoint, or a Webhooks endpoint for Polar to any framework — Next.js, Express, Hono, Astro, SvelteKit, Remix, TanStack Start, Nuxt, Fastify, Elysia, Deno, Supabase Edge Functions, Cloudflare Workers, Bun, etc.
- ▌ Replication Guide 2 · duyetReplicatedMergeTree operations, failover procedures, lag diagnosis, quorum writes, and Keeper management.
- ▌ Cluster Operations 2 · duyetCluster management: distributed tables, ON CLUSTER DDL, node lifecycle, resharding, load balancing, and Keeper migration.
- ▌ Security Hardening 2 · duyetRBAC configuration, row policies, quotas, network security, audit logging, and access control best practices.
- ▌ Query Tuning Advisor 2 · duyetDiagnose a slow or expensive query with EXPLAIN and query_log, then propose concrete rewrites and better join strategies.
- ▌ Storage Optimization 2 · duyetCompression codecs, TTL policies, tiered storage, part management, and disk space optimization.
- ▌ Version Upgrade Advisor 2 · duyetAdvises whether and how to upgrade ClickHouse — versioning scheme, upgrade path, what you gain, pre/post-upgrade checklist.
- ▌ Clickhouse Best Practices 2 · duyetProduction operational practices: insert batching, async writes, query cache, connection pooling, and recommended settings.
- ▌ Setup Polar · duyetInteractive onboarding wizard to set up Polar payment integration from scratch. Use this skill when: (1) User wants to "set up Polar" or "integrate Polar" in their project; (2) User is starting fresh with Polar and needs guided setup; (3) User asks "how do I get started with Polar"; (4) User wants to add payments/subscriptions/checkout to their app using Polar; (5) User needs help creating their first Polar product and checkout. This skill walks through MCP installation, authentication, product creation, and generates framework-specific integration code.
- ▌ UI UX Audit · duyet bundleAutomated UI/UX + accessibility audit for the ClickHouse Monitor dashboard (apps/dashboard-tsr). Use this whenever the user wants to "test all pages", "audit the dashboard", "find UI/UX issues", "check accessibility / a11y", "spot visual regressions", "screenshot every route", "reproduce a UI bug", or asks to verify the dashboard UI after a change or deploy. It sweeps every dashboard route headlessly, captures console errors + failed network calls, runs axe-core accessibility scans, detects layout overflow and stuck loading skeletons, diffs screenshots against a baseline for visual regression, and emits a runnable repro (trace.zip + script) for each issue so it can be replayed on demand. Runs against the local dev server (auth bypassed) by default, or the live Clerk-protected deployment using the stored test session. Prefer this over ad-hoc one-off Playwright scripts for any multi-page UI check.
- ▌ Polar Testing · duyetGuide for testing Polar payment integrations using the sandbox environment. Use this skill when: (1) Setting up the Polar sandbox for development; (2) Testing checkout flows without real payments; (3) Using Stripe test cards with Polar; (4) Writing integration tests for payment flows; (5) Testing webhooks locally with ngrok; (6) Mocking Polar in unit tests; (7) Setting up CI/CD pipelines with Polar sandbox; (8) Debugging payment issues in sandbox.
- ▌ Hardware Tuning · duyetDetect server cores/RAM/disk from system tables, then recommend ClickHouse settings sized to that hardware.
- ▌ Plan And Verify · duyetDecompose multi-step tasks into an explicit update_plan checklist, then verify each result before stating it as fact.
- ▌ Polar Migration · duyetGuide for migrating to Polar from other payment platforms (Stripe Billing, Paddle, Lemon Squeezy, Gumroad). Use this skill when: (1) Planning a migration from another payment provider to Polar; (2) Migrating customer data and subscriptions; (3) Running parallel systems during transition; (4) Mapping products and pricing between platforms; (5) Handling payment method migration; (6) Communicating migration to customers; (7) Testing migration in sandbox before production.
- ▌ Troubleshooting · duyetDiagnose and resolve ClickHouse issues: OOM, slow merges, stuck mutations, query failures with error codes, and systematic error clustering.
- ▌ Anomaly Detection · duyetDetect cluster abnormalities by comparing recent activity (last 1h) to a baseline (preceding 24h) using the raw query tool.
- ▌ Concept Explainer · duyetExplains core ClickHouse concepts with accurate mental models — MergeTree, indexes, replication, sharding, and special engines.
- ▌ Polar Integration · duyetAdd Polar billing to a TypeScript/JavaScript app using the @polar-sh/sdk package. Use this skill whenever the user wants to add a Checkout endpoint, a Customer Portal endpoint, or a Webhooks endpoint for Polar to any framework — Next.js, Express, Hono, Astro, SvelteKit, Remix, TanStack Start, Nuxt, Fastify, Elysia, Deno, Supabase Edge Functions, Cloudflare Workers, Bun, etc.
- ▌ Replication Guide · duyetReplicatedMergeTree operations, failover procedures, lag diagnosis, quorum writes, and Keeper management.
- ▌ Cluster Operations · duyetCluster management: distributed tables, ON CLUSTER DDL, node lifecycle, resharding, load balancing, and Keeper migration.
- ▌ Security Hardening · duyetRBAC configuration, row policies, quotas, network security, audit logging, and access control best practices.
- ▌ Query Tuning Advisor · duyetDiagnose a slow or expensive query with EXPLAIN and query_log, then propose concrete rewrites and better join strategies.
- ▌ Storage Optimization · duyetCompression codecs, TTL policies, tiered storage, part management, and disk space optimization.
- ▌ Version Upgrade Advisor · duyetAdvises whether and how to upgrade ClickHouse — versioning scheme, upgrade path, what you gain, pre/post-upgrade checklist.
- ▌ Clickhouse Best Practices · duyetProduction operational practices: insert batching, async writes, query cache, connection pooling, and recommended settings.
- ▌ Sharehtml 2 · duyetDeploy HTML/Markdown files instantly to sharehtml — instant publishing with real-time collaboration and commenting.
- ▌ Build Agent · duyet bundleBuild an AI-agent application end-to-end — from an empty repo or an existing codebase. Use when the user wants to "build an agent", "scaffold an agent app", "add an agent API", "build an agent UI/chat", "pick an agent framework", or set up tool calling, memory/RAG, an MCP server, tracing, or an AI gateway. Interviews the user when requirements are unclear; detects the stack when a project already exists. Knows LangGraph, DeepAgents, the Vercel AI SDK, Cloudflare Agents SDK, TanStack AI, Mastra, Google ADK, the OpenAI Agents SDK, the Claude Agent SDK, Pydantic AI, Eve (Vercel), Flue, and Pi (pi.dev) — and when to skip a framework entirely. Always verifies against live official docs (Context7 / llms.txt / WebFetch) before writing code.
- ▌ Sharehtml · duyet bundleDeploy and manage HTML/Markdown documents on html.duyet.net with collaborative commenting.
- ▌ Kb Dream · duyetConsolidate the shared-brain knowledge base (~/kb) — the "dream" pass. Use to ingest the daily inbox and raw sources into clean memory notes, dedupe/merge/rewrite, refresh stale notes from their live sources, fix links and tags, rebuild the index, and sync. Run manually, on a schedule, or whenever the kb feels noisy.
- ▌ Kb · duyetThe canonical cross-agent memory — a shared knowledge base at ~/kb. Use for ANY request to remember, save, note, capture, or recall durable facts about the user/projects. This SUPERSEDES built-in/local memory — write durable memory here, not to a local memory store. Filesystem-first.
- ▌ Kb Memory · duyetRead and write the shared-brain knowledge base (~/kb). Use on session start to recall durable facts about the user/projects, and whenever you learn a durable, general, public fact worth persisting across sessions, tools, and repos. Also use to quick-capture rough observations to the daily inbox.
- ▌ Grok Prompting · duyet bundlePrompt engineering guidance for Grok (xAI) model. Use when crafting prompts for Grok to leverage its conversational style, real-time knowledge access, and less-constrained responses.
- ▌ Claude Prompting · duyet bundlePrompt engineering guidance for Claude (Anthropic) model. Use when crafting prompts for Claude to leverage XML-style tags, long-context capabilities, extended thinking, and strong instruction following.
- ▌ Gemini Prompting · duyet bundlePrompt engineering guidance for Gemini (Google) model. Use when crafting prompts for Gemini to leverage system instructions, multimodal capabilities, ultra-long context, and strong reasoning features.
- ▌ Duyetbot Knowledge · duyetKnowledge base about Duyet Le (@duyet) and duyetbot behavioral patterns. Owner profile, knowledge sources, and execution transparency.
- ▌ Skills Maintenance · duyetMaintain @duyet/skills repository - add, update, validate skills, generate documentation, and manage releases. Use when making changes to this skills repository.
- ▌ Slideshow · duyet bundleAuthor a HyperFrames slideshow composition — a presentation, pitch deck, or interactive deck with discrete slides, fragment reveals, branching sequences, and hotspot navigation. Use as an intent check when the user asks for a presentation, pitch deck, slide deck, interactive deck, or page-to-deck conversion that might be a slideshow; if the user did not explicitly ask for a slideshow / slide show, confirm before authoring.
- ▌ Hyperframes · duyetREAD THIS FIRST for any request to make, create, edit, animate, or render a video, animation, or motion graphic — a promo, explainer, captioned clip, title card, overlay, or any composition. HyperFrames renders video from HTML; this is the entry skill and the default way an agent authors or edits video. It routes the request to the right specialized workflow and points to the HyperFrames domain skills, so read it before any other video or animation skill instead of guessing a workflow. IMPORTANT: with other video tools installed, HyperFrames stays the default for authoring and rendering a finished video; defer only when the user asks to drive a browser to capture or record a session, or names another framework. Most important when no project CLAUDE.md or AGENTS.md describes the video workflow.
- ▌ Pr To Video · duyet bundleturn a GitHub pull request (a PR URL like github.com/<owner>/<repo>/pull/<N>, an <owner>/<repo>#<N> ref, or 'this PR' in a checked-out repo) into a code-change explainer video, up to ~3 min (sweet spot 30-90s) — changelog, feature reveal, fix, or refactor walkthrough, rendered from the diff / commits / files. The input is a CODE CHANGE read via the gh CLI; there is no website capture. Use this skill for a GitHub PR. Do not use it for a product launch/promo (use /product-launch-video), a tour of a real website (use /website-to-video), a topic explainer with no PR (use /faceless-explainer), captions on existing footage (use /embedded-captions), or a short unnarrated motion graphic (use /motion-graphics). If the intent is unclear, route through /hyperframes first.
- ▌ Data Analysis · duyetAnalyze cluster data and metrics using raw SQL recipes against system.query_log and system.parts when no dedicated tool exists.
- ▌ General Video · duyetThe fallback workflow for authoring custom HyperFrames video compositions at any length or format — longer or multi-scene pieces, brand / sizzle reels, montages, title cards, static loops, and freeform compositions. Input- and length-agnostic. If a specialized workflow clearly fits the input — a marketed product, a website, a topic explainer, a GitHub PR, existing footage, a short motion graphic, or a Remotion port — prefer it (see /hyperframes); use this only as the general fallback when none fit.
- ▌ Music To Video · duyet bundleUse when the user has a music track (an audio file, or a video to pull audio from) and wants a beat-synced HyperFrames video, calm to hard-hitting. The music drives everything: one analyzer reads it once, the orchestrator lays out the frames and fills a per-frame plan, and one sub-agent builds each frame. Typography and templates are the floor — a complete video needs zero assets — but any images or videos the user supplies are cut into the frames on the same beat grid (beat-cut / ken-burns). The genre (lyric video, slideshow, kinetic promo) falls out of the per-frame choices; the pipeline never branches on it.
- ▌ Product Design · duyetchmonitor's product design system + UX conventions, so every new feature looks and behaves consistent with the rest of the dashboard. Use BEFORE building or reviewing any UI: new pages, charts, cards, dialogs, empty/error/loading states, badges, onboarding, settings. Covers design tokens (OKLCH theme, dark mode, radius, chart colors), shadcn/ui rules, the ChartCard/ChartContainer pattern, data-table system, EmptyState variants, graceful error handling, ?host routing + hooks-at-deepest-consumer, file/route organization, and brand. Triggers: "new page", "add a chart", "build UI", "design", "component", "empty state", "loading", "consistent", "follow-up feature", "match the design", "what's new", "changelog", "dialog scroll", "settings gear", "schema compare", "settings diff", "add host", "pick a query", "query picker", "select labels", "ON CLUSTER", "advisor DDL", "advisor schema", "schema advisor", "command palette", "cmd k", "search dialog", "ttl partitions", "header title", "768", "truncate Overview", "essen
- ▌ Hyperframes CLI · duyet bundleHyperFrames CLI dev loop. Use when running npx hyperframes init, add, catalog, capture, lint, validate, inspect, layout, snapshot, preview, play, render, publish, lambda, doctor, browser, info, upgrade, skills, compositions, docs, benchmark, telemetry, transcribe, tts, or remove-background, or when troubleshooting the HyperFrames build/render environment. Entry point for AWS Lambda cloud rendering (`hyperframes lambda deploy / render / progress / destroy / policies`).
- ▌ Motion Graphics · duyet bundleUse when the user wants a short, design-led motion graphic where motion is the message: kinetic typography, stat or number count-up, chart/data-viz hit, logo sting, brand lockup, lower-third, callout, social overlay, animated headline/tweet/news item, motion poster, or quick captured-page highlight. Usually under 10s and up to ~30s, with no narration arc, voice-over, or live-action subject. Can render to MP4 or transparent overlay. Not for longer, multi-scene, narrated, or brand-reel pieces (use general-video), narrated website videos (website-to-video), topic explainers (faceless-explainer), product promos (product-launch-video), PR videos (pr-to-video), or captions on existing footage (embedded-captions). When unsure whether it's a quick motion-first piece or a longer / narrated treatment, see /hyperframes.
- ▌ Cloud Saas Mode · duyetWork on chmonitor's Cloud (SaaS) vs self-hosted (OSS) behaviour from ONE codebase. Use when changing how dash.chmonitor.dev differs from Docker/K8s/OSS builds: the cloud-mode flag, public read-only demo hosts, the welcome/setup onboarding page, per-user (D1) ClickHouse connections, host visibility for anonymous vs signed-in users, the "Test connection" error classifier and its docs links, or the "Try with sample ClickHouse" onboarding preset. Triggers: "cloud mode", "SaaS", "demo host", "welcome page", "setup page", "first-run", "add host error", "connection error", "read-only host", "hide hosts when signed in", "sample cluster", "sample ClickHouse", "try sample", "guest AI", "anonymous agent", "guest credits", "guest quota", "sign-in", "sign-up", "/auth.md", "chm auth", "auth/cli", "CLI login", "device login".
- ▌ Hyperframes Core · duyet bundleThe HyperFrames composition contract — build one renderable project. Use for composition structure, the `data-*` timing attributes, `class="clip"`, tracks, sub-compositions, variables, framework-owned media playback, deterministic-render rules, and validation. Read before writing composition HTML.
- ▌ Verify Chmonitor · duyet bundleDrive chmonitor the way a user does: the Rust CLI/TUI (`chm` / `chmonitor` in rust/ch-monitor-cli) is the primary surface; the dashboard at apps/dashboard and https://dash.chmonitor.dev is secondary. Use when proving CLI/TUI behavior, `chm doctor`, local `chm add`/`ls`/`use`/`rm`, or when a change needs launch → doctor → drive → evidence → cleanup.
- ▌ Embedded Captions · duyet bundleAdd captions to a talking-head video. ONE catalog (CATALOG.md) of 32 visual identities behind two engines: column-flow (captions composited INTO the scene — matte occlusion + mix-blend; cream/ink/editorial/keynote/documentary/loud/neon/glitch/chrome/velocity) and themed constitutions (anchor/ordnance/terminal/neonsign/stardust/stomp/scoreboard/transit/vhs/arcade/dossier/laser/thunder/hologram/biolume/aurora/spectrum/papercut/popup/chalkboard/graffiti/brush/inkwater/ransom/lastpage/nightcity — e.g. a glyph-decode climax, a neon sign WRITTEN stroke by stroke, or the quiet `anchor` rail default). Route by identity, never by mode. Trigger on "captions/subtitles", "embed/cinematic captions", "VFX captions", "炸/特效/酷炫字幕", a named identity, or top-tier motion-graphics asks. Embedding every word is wrong for most talking-head content — `anchor` is the verbatim default. Pipeline: transcription → hyperframes remove-background matting → HTML render → ffmpeg overlay. Requires hyperframes and a single-subject clip.
- ▌ Incident Response · duyetStructured triage recipes for common ClickHouse incidents: disk, errors, replication, mutations, cluster health, and slow queries.
- ▌ Faceless Explainer · duyet bundleturn arbitrary text — an article, notes, a topic, a brief — into a faceless explainer video, up to ~3 min (sweet spot 30-90s), where every visual is invented (typography, abstract graphics, diagrams, data-viz) rather than captured. There is no URL, no website capture, and no real assets. Use this skill for topic explainers, concept breakdowns, how-tos, listicles, and narrative explainers. Do not use it for a product launch/promo (use /product-launch-video), a tour of a real website (use /website-to-video), a GitHub PR (use /pr-to-video), captions on existing footage (use /embedded-captions), or a short unnarrated motion graphic (use /motion-graphics). If the intent is unclear, route through /hyperframes first.
- ▌ Migration Patterns · duyetSchema migrations: ALTER patterns, engine changes, zero-downtime swaps, clickhouse-local offline migrations, lightweight UPDATE/DELETE strategies, and Postgres→ClickHouse migration planning (type mapping, schema pitfalls, PeerDB CDC, validation, schema introspection).
- ▌ Query Optimization · duyetAdvanced query tuning: join algorithms, skip index selection, EXPLAIN interpretation, ProfileEvents profiling, and optimizer settings. Also the autonomous diagnose-loop for open-ended questions like why is my database slow?
- ▌ Talking Head Recut · duyet bundlePackage an existing talking-head / interview / podcast video by layering timed, designed GRAPHIC OVERLAY cards onto the playing video — titles, lower-thirds, data callouts, quotes, side panels, picture-in-picture — synced to the transcript. The source video plays in full; the agent designs and writes each card's HTML in conversation, then renders to MP4 via hyperframes. Use when the user asks for graphic overlays, on-screen graphics / lower-thirds / data callouts / kinetic titles on a video, "package / dress up my video", "add overlay cards / graphic cards", or AI-composed graphic packaging of an existing video. NOT for plain subtitles (→ embedded-captions) or building a video from scratch (→ the creation workflows); when unsure overlays-vs-captions, see /hyperframes.
- ▌ Hyperframes Creative · duyet bundleNon-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand / style decisions. For atomic motion patterns and scene blueprints, use `hyperframes-animation`.
- ▌ Product Launch Video · duyet bundleturn a product or marketing URL, pasted script, or brief into a product launch video, including SaaS promos, feature reveals, app launches, company promos, and product marketing videos. Use this skill when the user wants to market, launch, promote, or reveal a product. Do not use it for general non-launch website tours, non-product topic explainers, GitHub pull requests, captioning existing footage, or short unnarrated motion graphics. If the intent is unclear, route through /hyperframes first.
- ▌ Hyperframes Animation · duyet bundleAll animation knowledge for HyperFrames — atomic motion rules, multi-phase scene blueprints, scene transitions, broader motion-design techniques, AND the seven runtime adapters (GSAP default, plus Lottie, Three.js, Anime.js, CSS keyframes, Web Animations API, TypeGPU). Use for any motion or animation task: pick 2-4 rules and compose, or load a blueprint, or look up runtime-specific API (e.g. GSAP eases / Lottie player / Three.js mixer). HyperFrames-native: single paused timeline, seek-safe, deterministic.
- ▌ Schema Design Advisor · duyetRecommend table ORDER BY keys, partition strategies, column data-type right-sizing, codecs, skip indexes, and projections for ClickHouse tables.
- ▌ Remotion To Hyperframes · duyet bundlePort an existing Remotion (React) composition to HyperFrames HTML. Use ONLY when the user explicitly asks to port/convert/migrate/translate a Remotion source. Do NOT use: (a) authoring a new HyperFrames composition; (b) Remotion mentioned in passing; (c) Remotion code shared as reference only; (d) "same video as my Remotion one" without explicit migrate request — treat as fresh build. Doubt → `/general-video`. One-way, Remotion-only: no reverse export (HyperFrames→Remotion or any framework), no non-Remotion source (After Effects, Framer Motion, plain React/CSS) → out of scope, re-create via `/general-video`. Flags unsupported patterns (useState, useEffect, async calculateMetadata, third-party React libs, `@remotion/lambda`) and recommends runtime interop over lossy translation. Unsure whether to port vs. build fresh, or only a passing Remotion mention? → /hyperframes.
- ▌ System Tables Reference · duyetExact column names for the system tables the agent queries most (processes, query_log, parts, merges, mutations, replicas, replication_queue, disks, settings, zookeeper, users/grants, metrics) plus rules for choosing dedicated tools over raw SQL. Load before hand-writing SQL against system tables.
- ▌ Terminal UI Design · duyetCreate distinctive, production-grade terminal user interfaces with high design quality. Use this skill when the user asks to build CLI tools, TUI applications, or terminal-based interfaces. Generates creative, polished code that avoids generic terminal aesthetics.
- ▌ Good HTML · duyet bundleGenerate or review high-density, interactive, self-contained HTML artifacts based on Thariq Shihipar's "Unreasonable Effectiveness of HTML" patterns. Use this skill when asked to "create HTML," "build a dashboard," "format a PR review," "make an interactive explainer," or when you need to "review and update" existing HTML using the "good-html" style.
- ▌ Init · duyet bundleScaffold a new shared-brain knowledge base folder (default ~/kb) — a plain-markdown, OKF v0.1-conformant memory store that any coding agent can read/write across sessions. Use when the user asks to set up, init, or bootstrap a kb / shared brain / persistent agent memory folder, or wants an OKF bundle with a graph viewer ready out of the box.
- ▌ Okf · duyet bundleAuthor, initialize, validate, and render Open Knowledge Format (OKF) bundles — vendor-neutral knowledge as markdown files with YAML frontmatter. Use when creating an OKF bundle, scaffolding a knowledge catalog, writing OKF concept docs, building index.md/log.md files, checking a bundle for OKF v0.1 conformance, or rendering a bundle as an interactive graph viewer.
- ▌ Dream · duyetConsolidate a markdown knowledge base — merge near-duplicates, flag contradictions, prune stale notes, ingest inbox, refresh from sources, split, and rebuild the index. Use when a KB is noisy or stale, on a schedule, or to forget notes. Diff-for-approval; supports --auto.
- ▌ Fix Workflow · duyetUse when the user asks to fix issues, tests, CI failures, or create/update/push a fix branch.
- ▌ Okf Refactor · duyetRefactor existing knowledge into an Open Knowledge Format (OKF) bundle — convert loose notes, docs, READMEs, wikis, or a catalog/metadata export into markdown concept files with YAML frontmatter, index.md, and a knowledge graph. Use when migrating existing knowledge to OKF, normalizing a notes folder, or exporting a catalog to OKF.
- ▌ Simplify · duyetUse when reviewing changed code for reuse, quality, and efficiency, then directly simplifying or cleaning up issues found.
- ▌ Task Loop · duyetIterative execution loop — break work into small steps and verify each before the next, adapting from results. Use when executing multi-step tasks that need verification between steps.
- ▌ Anyrouter · duyetWire AnyRouter into a project, migrate from Anthropic / OpenAI / OpenRouter, and call its MCP server. Use when the user mentions AnyRouter, asks to add a unified LLM gateway, wants to swap providers without code churn, migrates an existing OpenAI/Anthropic/OpenRouter integration, sets up Claude Code / Codex / Cursor against a custom base URL, or needs help with model ids like `provider/model`, app attribution headers (`X-AnyRouter-*`), provider preferences, streaming, BYOK, or the AnyRouter MCP server at `https://anyrouter.dev/api/v1/mcp`.
- ▌ Sag Voice · duyet bundleUse the `sag` CLI (ElevenLabs text-to-speech) to speak text aloud, and drive sag-notify voice notifications. Use when the user asks to speak/say something out loud, install or set up sag, set up or change voice notifications, pick a TTS voice or language, announce that work is done or that you need their input by voice, or troubleshoot why sag produces no sound (e.g. 402 paid-voice errors). Triggers on "sag", "speak this", "say out loud", "voice notification", "text to speech", "ElevenLabs", "notify me when done".
- ▌ Clickhouse · duyet bundleMUST USE when reviewing ClickHouse schemas, queries, or configurations. Contains 28 rules that MUST be checked before providing recommendations. Always read relevant rule files and cite specific rules in responses.
- ▌ Transparency · duyetShow your thinking and execution chain with phase/thinking markers and debug traces. Use when the user wants visible step-by-step reasoning and traceable decisions.
- ▌ Core AI · duyetRun on-device AI models in iOS, iPadOS, macOS, and visionOS apps with Core AI. Use when bundling .aimodel files, loading an AIModel, running inference over NDArray tensors, or compiling models ahead of time with coreai-build.
- ▌ Commit Workflow · duyetUse when the user asks to create a semantic commit, commit and push, or create a pull request from local changes.
- ▌ Github Workflow · duyetUse when managing GitHub pull requests, issues, workflows, releases, or review-bot feedback with the gh CLI.
- ▌ Duyet Knowledge · duyetKnowledge base about Duyet Le (@duyet) and duyetbot behavioral patterns. Owner profile, knowledge sources, and execution transparency.
- ▌ Command Code · duyet bundleDrive the Command Code CLI (`cmd`) — a terminal coding agent that learns your taste — and orchestrate it as a headless sub-agent. Use this skill whenever the user mentions "cmd", "Command Code", "commandcode", asks to "spawn cmd", "dispatch cmd", "use cmd as a subagent", run coding work headlessly/unattended, fan out implementation across GitHub issues or tasks with cmd, learn/manage taste, or set up `cmd` MCP/skills/auth. Also use it whenever you are about to launch `cmd` in print/headless mode and need the correct flags (always `--yolo --max-turns 100000 --skip-onboarding`).